Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models

• URL: http://arxiv.org/abs/2509.22221v1
• Date: Fri, 26 Sep 2025 11:34:42 GMT
• Title: Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
• Authors: Jiaqi Liu, Lang Sun, Ronghao Fu, Bo Yang,
• Abstract summary: Vision-Language Models (VLMs) in remote sensing often fail at complex analytical tasks.<n>We introduce the Perceptually-Grounded Geospatial Chain-of-Thought (Geo-CoT)<n>Geo-CoT is a framework that models remote sensing analysis as a verifiable, multi-step process.
• Score: 8.021952962029165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models (VLMs) in remote sensing often fail at complex analytical tasks, a limitation stemming from their end-to-end training paradigm that bypasses crucial reasoning steps and leads to unverifiable outputs. To address this limitation, we introduce the Perceptually-Grounded Geospatial Chain-of-Thought (Geo-CoT), a framework that models remote sensing analysis as a verifiable, multi-step process. We instill this analytical process through a two-stage alignment strategy, leveraging Geo-CoT380k, the first large-scale dataset of structured Geo-CoT rationales. This strategy first employs supervised fine-tuning (SFT) to instill the foundational cognitive architecture, then leverages Group Reward Policy Optimization (GRPO) to refine the model's reasoning policy towards factual correctness. The resulting model, RSThinker, outputs both a final answer and its justifying, verifiable analytical trace. This capability yields dominant performance, significantly outperforming state-of-the-art models across a comprehensive range of tasks. The public release of our Geo-CoT380k dataset and RSThinker model upon publication serves as a concrete pathway from opaque perception towards structured, verifiable reasoning for Earth Observation.

Related papers

• On Multi-Step Theorem Prediction via Non-Parametric Structural Priors [50.16583672681106]
  In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL)<n>We propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference.<n>Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models.
  arXiv  Detail & Related papers  (2026-03-05T06:08:50Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents [68.85365034738534]
  We introduce a unified framework for developing tool-augmented geospatial agents trained on satellite imagery, natural-language queries, and detailed reasoning traces.<n>The training pipeline relies on supervised fine-tuning over structured reasoning trajectories, aligning the model with verified multistep tool interactions.<n>The accompanying corpus comprises 14,538 training and 1,169 evaluation instances, with more than 100K reasoning steps in the training split and over 7K reasoning steps in the evaluation split.
  arXiv  Detail & Related papers  (2026-02-19T18:59:54Z)
• GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics [91.17301794848025]
  This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions.<n>Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain concerns because of their reliance on AI-generated chain-of-thought (CoT) data and training strategies.
  arXiv  Detail & Related papers  (2026-02-13T04:48:05Z)
• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs [53.199517625701475]
  CoG is a training-free framework inspired by Dual-Process Theory that mimics the interplay between intuition and deliberation.<n>CoG significantly outperforms state-of-the-art approaches in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-01-16T07:27:40Z)
• GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning [12.987952829880363]
  GeoReason is a framework designed to synchronize internal thinking with final decisions.<n>We first construct GeoReason-Bench, a logic-driven dataset containing 4,000 reasoning trajectories.<n>We then formulate a two-stage training strategy: (1) Supervised Knowledge Initialization to equip the model with reasoning syntax and domain expertise, and (2) Consistency-Aware Reinforcement Learning to refine deductive reliability.
  arXiv  Detail & Related papers  (2026-01-07T17:26:41Z)
• GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding [14.436063587920005]
  We introduce GeoDiT, the first diffusion-based vision-language model tailored for the geospatial domain.<n>It achieves significant gains in image captioning, visual grounding, and multi-object detection.<n>Our work validates that aligning the generative process with the data's intrinsic structure is key to unlocking superior performance in complex geospatial analysis.
  arXiv  Detail & Related papers  (2025-12-02T07:59:46Z)
• Geo-R1: Unlocking VLM Geospatial Reasoning with Cross-View Reinforcement Learning [26.869573782008217]
  We introduce Geo-R1, a reasoning-centric post-training framework that unlocks geospatial reasoning in vision-language models.<n>In the scaffolding stage, Geo-R1 instills a geospatial thinking paradigm" via supervised fine-tuning on synthetic chain-of-thought exemplars.<n>In the elevating stage, it uses GRPO-based reinforcement learning on a weakly-supervised cross-view pairing proxy.
  arXiv  Detail & Related papers  (2025-09-29T21:34:55Z)
• Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning [37.90271368636318]
  Referring expression understanding in remote sensing poses unique challenges.<n>We propose Geo-R1, a reasoning-centric reinforcement fine-tuning (RFT) paradigm for few-shot geospatial referring.<n>We validate Geo-R1 on three carefully designed few-shot geospatial referring benchmarks, where our model consistently and substantially outperforms SFT baselines.
  arXiv  Detail & Related papers  (2025-09-26T07:01:12Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models [27.848962405476108]
  New pipeline constructs reasoning-oriented geo-localization dataset, MP16-Reason, using diverse social media images.<n>We introduce GLOBE, Group-relative policy optimization for Locatability assessment and optimized visual-clue reasoning.<n>Results demonstrate that GLOBE outperforms state-of-the-art open-source LVLMs on geo-localization tasks.
  arXiv  Detail & Related papers  (2025-06-17T16:07:58Z)
• Expert Insight-Based Modeling of Non-Kinetic Strategic Deterrence of Rare Earth Supply Disruption:A Simulation-Driven Systematic Framework [3.5516803380598074]
  This study constructs a quantifiable modelling framework to simulate non-kinetic strategic deterrence pathways in rare earth supply disruption scenarios.<n>Data is derived from expert interviews and scenario analyses centered on U.S.-China dynamics in ISR, electronic warfare, and rare earth control.<n>Results show institutional signals have strong tempo and path-coupling effects, capable of causing rapid degradation of strategic capabilities.
  arXiv  Detail & Related papers  (2025-06-13T10:18:59Z)
• Reinforced Reasoning for Embodied Planning [18.40186665383579]
  Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals.<n>We introduce a reinforcement fine-tuning framework that brings R1-style reasoning enhancement into embodied planning.
  arXiv  Detail & Related papers  (2025-05-28T07:21:37Z)
• Chain-of-Retrieval Augmented Generation [72.06205327186069]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mapping [19.307294875969827]
  This paper introduces AI foundation models and their defining characteristics. We evaluate the performance of large AI vision models, especially Meta's Segment Anything Model (SAM) The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping.
  arXiv  Detail & Related papers  (2024-01-16T19:10:09Z)
• GEO-Bench: Toward Foundation Models for Earth Monitoring [139.77907168809085]
  We propose a benchmark comprised of six classification and six segmentation tasks. This benchmark will be a driver of progress across a variety of Earth monitoring tasks.
  arXiv  Detail & Related papers  (2023-06-06T16:16:05Z)
• Generalization Properties of Optimal Transport GANs with Latent Distribution Learning [52.25145141639159]
  We study how the interplay between the latent distribution and the complexity of the pushforward map affects performance. Motivated by our analysis, we advocate learning the latent distribution as well as the pushforward map within the GAN paradigm.
  arXiv  Detail & Related papers  (2020-07-29T07:31:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.